M.J. Ribeiro
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
39 records found
1
Unified Framework for Scalable Vertiport Allocation with Heterogeneous Fleet Sizing
Case Study on the Republic of Ireland
Advanced Air Mobility (AAM) is expected to transform urban and regional transportation. However, its successful deployment hinges on robust infrastructure planning that balances operational efficiency with scalable growth. Current vertiport allocation models typically deliver single, static network solutions without considering phased growth or aircraft performance limitations. This gap is addressed by presenting a unified framework that generates a scalable vertiport allocation plan in conjunction with system-performance-based heterogeneous fleet sizing. First, potential vertiport networks are generated through a distance-based agglomerative clustering algorithm applied to the census-based synthetically generated demand. Second, the mean vertiport network is established, and undergoes an elimination procedure aimed at maximizing passenger km travelled, to establish phased growth of the vertiport network. In order to determine the optimal development of the fleet as the network grows, the framework employs an agent-based simulation and conducts a parameter sweep across all combinations of vertiport network size, fleet size and fleet composition. This framework is validated on a use case on the Republic of Ireland. The results demonstrate the ability of the framework to deliver a demand-driven phased network introduction and expansion strategy, while identifying the optimal fleet size and composition at each growth stage. This approach provides stakeholders with a replicable foundation for capital allocation and regulatory planning in emerging AAM markets.
...
Advanced Air Mobility (AAM) is expected to transform urban and regional transportation. However, its successful deployment hinges on robust infrastructure planning that balances operational efficiency with scalable growth. Current vertiport allocation models typically deliver single, static network solutions without considering phased growth or aircraft performance limitations. This gap is addressed by presenting a unified framework that generates a scalable vertiport allocation plan in conjunction with system-performance-based heterogeneous fleet sizing. First, potential vertiport networks are generated through a distance-based agglomerative clustering algorithm applied to the census-based synthetically generated demand. Second, the mean vertiport network is established, and undergoes an elimination procedure aimed at maximizing passenger km travelled, to establish phased growth of the vertiport network. In order to determine the optimal development of the fleet as the network grows, the framework employs an agent-based simulation and conducts a parameter sweep across all combinations of vertiport network size, fleet size and fleet composition. This framework is validated on a use case on the Republic of Ireland. The results demonstrate the ability of the framework to deliver a demand-driven phased network introduction and expansion strategy, while identifying the optimal fleet size and composition at each growth stage. This approach provides stakeholders with a replicable foundation for capital allocation and regulatory planning in emerging AAM markets.
Conference paper
(2026)
-
E. Süülker, P.R.J.R. Lothaller, M.J. Ribeiro, Junzi Sun, Jasper de Wilde, Alexander Piva
During the transition from the en-route phase to landing, an aircraft’s flight time is subject to significant uncertainty. This uncertainty arises primarily from unpredictable weather, varying aircraft performance characteristics, and the human element in executing ATC instructions. Improved estimation of the approach phase duration could yield significant benefits for airline fuel planning and flight scheduling, yet current practice still largely relies on fixed deterministic buffers. Existing work on arrival delay prediction focuses on deterministic models at smaller forecast horizons during the airborne phase.
This paper develops and validates an explainable probabilistic forecasting model for flight duration within the Amsterdam Schiphol (AMS) Flight Information Region (FIR), with a forecast moment in the pre-departure phase. The primary objective is to forecast the duration within the AMS FIR using information available at planning, while providing interpretable contributors of delay that can be clearly communicated to flight dispatchers and pilots.
Results show that our model achieves a reduced MAE of 33% and a reduced RMSE of 26% relative to the current operational baseline, while capturing about one third of the variance in FIR duration (R² = 0.33). Additionally, quantile-based transit time forecasts can provide airlines with a more risk-aware basis for fuel and schedule planning than fixed deterministic buffers. However, the relatively low R² shows that a substantial share of the variation in FIR duration remains unexplained, largely associated with tactical ATC interventions that occur under otherwise acceptable weather and capacity conditions. ...
This paper develops and validates an explainable probabilistic forecasting model for flight duration within the Amsterdam Schiphol (AMS) Flight Information Region (FIR), with a forecast moment in the pre-departure phase. The primary objective is to forecast the duration within the AMS FIR using information available at planning, while providing interpretable contributors of delay that can be clearly communicated to flight dispatchers and pilots.
Results show that our model achieves a reduced MAE of 33% and a reduced RMSE of 26% relative to the current operational baseline, while capturing about one third of the variance in FIR duration (R² = 0.33). Additionally, quantile-based transit time forecasts can provide airlines with a more risk-aware basis for fuel and schedule planning than fixed deterministic buffers. However, the relatively low R² shows that a substantial share of the variation in FIR duration remains unexplained, largely associated with tactical ATC interventions that occur under otherwise acceptable weather and capacity conditions. ...
During the transition from the en-route phase to landing, an aircraft’s flight time is subject to significant uncertainty. This uncertainty arises primarily from unpredictable weather, varying aircraft performance characteristics, and the human element in executing ATC instructions. Improved estimation of the approach phase duration could yield significant benefits for airline fuel planning and flight scheduling, yet current practice still largely relies on fixed deterministic buffers. Existing work on arrival delay prediction focuses on deterministic models at smaller forecast horizons during the airborne phase.
This paper develops and validates an explainable probabilistic forecasting model for flight duration within the Amsterdam Schiphol (AMS) Flight Information Region (FIR), with a forecast moment in the pre-departure phase. The primary objective is to forecast the duration within the AMS FIR using information available at planning, while providing interpretable contributors of delay that can be clearly communicated to flight dispatchers and pilots.
Results show that our model achieves a reduced MAE of 33% and a reduced RMSE of 26% relative to the current operational baseline, while capturing about one third of the variance in FIR duration (R² = 0.33). Additionally, quantile-based transit time forecasts can provide airlines with a more risk-aware basis for fuel and schedule planning than fixed deterministic buffers. However, the relatively low R² shows that a substantial share of the variation in FIR duration remains unexplained, largely associated with tactical ATC interventions that occur under otherwise acceptable weather and capacity conditions.
This paper develops and validates an explainable probabilistic forecasting model for flight duration within the Amsterdam Schiphol (AMS) Flight Information Region (FIR), with a forecast moment in the pre-departure phase. The primary objective is to forecast the duration within the AMS FIR using information available at planning, while providing interpretable contributors of delay that can be clearly communicated to flight dispatchers and pilots.
Results show that our model achieves a reduced MAE of 33% and a reduced RMSE of 26% relative to the current operational baseline, while capturing about one third of the variance in FIR duration (R² = 0.33). Additionally, quantile-based transit time forecasts can provide airlines with a more risk-aware basis for fuel and schedule planning than fixed deterministic buffers. However, the relatively low R² shows that a substantial share of the variation in FIR duration remains unexplained, largely associated with tactical ATC interventions that occur under otherwise acceptable weather and capacity conditions.
An optimization framework for the design and operation of efficient urban air mobility systems
An application in the Île-de-France region
Journal article
(2026)
-
Sam Randeraad, Marta Ribeiro, Jan Anne Annema, Gonçalo Homem de Almeida Correia
Urban Air Mobility (UAM) systems offer a three-dimensional transportation alternative by using low-altitude airspace, with the potential to reduce travel times and improve access to mobility in regions underserved by current transportation systems. To support efficient design and operation of UAM systems, we develop an integrated optimization framework in response to three interrelated challenges: (i) land use, aeronautical feasibility, community acceptance and other factors that restrict the number of potential locations for vertiports, (ii) bidirectional demand–supply interaction that needs to be considered, as the level of service influences demand for UAM and operators adjust the level of service in response to demand, and (iii) strong interactions between strategic decisions on the distribution of ground infrastructure, tactical decisions on eVTOL fleet size and operational decisions on dispatching and repositioning. Analyzing the decisions in isolation can lead to poor estimates of the overall system performance. The framework consists of (1) a knock-off criteria analysis model for the identification of a realistic set of candidate locations for vertiports, (2) integer programming models in which strategic, tactical and operational decision levels are modeled, and (3) pre-processing techniques to generate near-optimal solutions for real-world instances. By applying the framework in a large-scale real-world setting in the Île-de-France region, we demonstrate complex interactions between strategic, tactical, and operational decision levels and customer demand, revealing various trade-offs between operator profit and traveler generalized travel costs.
...
Urban Air Mobility (UAM) systems offer a three-dimensional transportation alternative by using low-altitude airspace, with the potential to reduce travel times and improve access to mobility in regions underserved by current transportation systems. To support efficient design and operation of UAM systems, we develop an integrated optimization framework in response to three interrelated challenges: (i) land use, aeronautical feasibility, community acceptance and other factors that restrict the number of potential locations for vertiports, (ii) bidirectional demand–supply interaction that needs to be considered, as the level of service influences demand for UAM and operators adjust the level of service in response to demand, and (iii) strong interactions between strategic decisions on the distribution of ground infrastructure, tactical decisions on eVTOL fleet size and operational decisions on dispatching and repositioning. Analyzing the decisions in isolation can lead to poor estimates of the overall system performance. The framework consists of (1) a knock-off criteria analysis model for the identification of a realistic set of candidate locations for vertiports, (2) integer programming models in which strategic, tactical and operational decision levels are modeled, and (3) pre-processing techniques to generate near-optimal solutions for real-world instances. By applying the framework in a large-scale real-world setting in the Île-de-France region, we demonstrate complex interactions between strategic, tactical, and operational decision levels and customer demand, revealing various trade-offs between operator profit and traveler generalized travel costs.
Industrial aircraft maintenance policies still rely on rigid, static slot structures that limit operational efficiency. Existing research has mainly addressed task (re-)allocation within a pre-defined number and duration of slots, while direct slot planning (jointly determining slot duration and allocation) remains difficult due to its combinatorial complexity. We propose a graph-based, reinforcement-learning framework that sequentially constructs maintenance task packages within a fixed planning horizon. A Graph Neural Network (GNN) encodes relations among tasks to inform a deep reinforcement learning (DRL) policy, which learns to group tasks into slots efficiently. This framework is trained and evaluated on operational data from a major European airline and benchmarked against a fixed-time Mixed-Integer Linear Programming (MILP) benchmark and the current industry practice. The results demonstrate that the model rapidly generates feasible schedules, and quantify trade-offs among interval spillage, panel reuse, and drop-out tasks relative to these benchmarks. Our model is able to decrease task spillage and increase panel reuse consistently. Finally, as the reward weights can be tuned to reflect an airline’s operational preferences, this framework provides a flexible decision-support tool for dynamic aircraft maintenance task packaging.
...
Industrial aircraft maintenance policies still rely on rigid, static slot structures that limit operational efficiency. Existing research has mainly addressed task (re-)allocation within a pre-defined number and duration of slots, while direct slot planning (jointly determining slot duration and allocation) remains difficult due to its combinatorial complexity. We propose a graph-based, reinforcement-learning framework that sequentially constructs maintenance task packages within a fixed planning horizon. A Graph Neural Network (GNN) encodes relations among tasks to inform a deep reinforcement learning (DRL) policy, which learns to group tasks into slots efficiently. This framework is trained and evaluated on operational data from a major European airline and benchmarked against a fixed-time Mixed-Integer Linear Programming (MILP) benchmark and the current industry practice. The results demonstrate that the model rapidly generates feasible schedules, and quantify trade-offs among interval spillage, panel reuse, and drop-out tasks relative to these benchmarks. Our model is able to decrease task spillage and increase panel reuse consistently. Finally, as the reward weights can be tuned to reflect an airline’s operational preferences, this framework provides a flexible decision-support tool for dynamic aircraft maintenance task packaging.
Conference paper
(2026)
-
Daniel Cisneros Acevedo, M.J. Ribeiro, I.I. de Pater, M.A.C. Arias Chao, Tim Rootliep
Combining physics-based and data-driven models for aeroengine condition monitoring has attracted increasing research interest in Prognostics and Health Management. Hybrid methods that incorporate physics-based models into deep neural networks typically rely on pre-trained surrogate models of the engine performance model, which serve as a differentiable proxy during training. However, constructing such surrogates requires extensive exploration of the parameter space to generate representative datasets, resulting in a rapidly increasing computational burden as the number of model parameters grows.
To address this limitation, we present TurboGrad, an open-source differentiable aeroengine performance model that reformulates the Gas Turbine Simulation Program (GSPy) in PyTorch. Because the performance model is tracked as a computation graph, gradients with respect to any model parameter follow directly via backpropagation. We compared TurboGrad against GSPy for a single-spool turbojet, finding relative errors within 0.3%. Furthermore, we demonstrate gradient-based estimation of compressor and turbine efficiencies, converging to the ground truth after 30 epochs.
TurboGrad is open-source and provides a differentiable foundation for integrating physics-based aeroengine models directly into deep learning pipelines. ...
To address this limitation, we present TurboGrad, an open-source differentiable aeroengine performance model that reformulates the Gas Turbine Simulation Program (GSPy) in PyTorch. Because the performance model is tracked as a computation graph, gradients with respect to any model parameter follow directly via backpropagation. We compared TurboGrad against GSPy for a single-spool turbojet, finding relative errors within 0.3%. Furthermore, we demonstrate gradient-based estimation of compressor and turbine efficiencies, converging to the ground truth after 30 epochs.
TurboGrad is open-source and provides a differentiable foundation for integrating physics-based aeroengine models directly into deep learning pipelines. ...
Combining physics-based and data-driven models for aeroengine condition monitoring has attracted increasing research interest in Prognostics and Health Management. Hybrid methods that incorporate physics-based models into deep neural networks typically rely on pre-trained surrogate models of the engine performance model, which serve as a differentiable proxy during training. However, constructing such surrogates requires extensive exploration of the parameter space to generate representative datasets, resulting in a rapidly increasing computational burden as the number of model parameters grows.
To address this limitation, we present TurboGrad, an open-source differentiable aeroengine performance model that reformulates the Gas Turbine Simulation Program (GSPy) in PyTorch. Because the performance model is tracked as a computation graph, gradients with respect to any model parameter follow directly via backpropagation. We compared TurboGrad against GSPy for a single-spool turbojet, finding relative errors within 0.3%. Furthermore, we demonstrate gradient-based estimation of compressor and turbine efficiencies, converging to the ground truth after 30 epochs.
TurboGrad is open-source and provides a differentiable foundation for integrating physics-based aeroengine models directly into deep learning pipelines.
To address this limitation, we present TurboGrad, an open-source differentiable aeroengine performance model that reformulates the Gas Turbine Simulation Program (GSPy) in PyTorch. Because the performance model is tracked as a computation graph, gradients with respect to any model parameter follow directly via backpropagation. We compared TurboGrad against GSPy for a single-spool turbojet, finding relative errors within 0.3%. Furthermore, we demonstrate gradient-based estimation of compressor and turbine efficiencies, converging to the ground truth after 30 epochs.
TurboGrad is open-source and provides a differentiable foundation for integrating physics-based aeroengine models directly into deep learning pipelines.
The development of realistic synthetic trajectory data is essential for the planning and validation of future Air Traffic Management concepts. Deep generative models have emerged as state-of-the-art methods for synthetic trajectory generation due to their ability to learn complex dynamics. In particular, Variational Autoencoders (VAEs) have gained significant attention because of their stable training. However, for the generated data to be trusted, model interpretability is crucial. A key aspect for interpretability is the analysis of the latent space, where the essential features and patterns of trajectory behavior are encoded. However, in practice, many latent dimensions remain weakly utilized or collapse toward the prior, limiting interpretability and effective use of latent capacity.
In this work, we study latent dimension activity in temporal VAEs trained on real-world aircraft trajectory data, with a specific focus on how Kullback-Leibler (KL) divergence regularization, a penalty added to the model’s loss function, affects the number of active latent dimensions. We adopt a temporal convolutional VAE with fixed latent dimensionality and formulate the KL divergence as an average over latent dimensions, thereby controlling the information content per dimension.
Additionally, we introduce a modified training objective that explicitly suppresses near-collapsed dimensions through masking and reweighting of the KL term. Our results show that this intervention significantly increases the number of active latent dimensions without degrading reconstruction accuracy. Ultimately, this will improve understanding of the decisions behind trajectory generation, enabling wider adoption. ...
In this work, we study latent dimension activity in temporal VAEs trained on real-world aircraft trajectory data, with a specific focus on how Kullback-Leibler (KL) divergence regularization, a penalty added to the model’s loss function, affects the number of active latent dimensions. We adopt a temporal convolutional VAE with fixed latent dimensionality and formulate the KL divergence as an average over latent dimensions, thereby controlling the information content per dimension.
Additionally, we introduce a modified training objective that explicitly suppresses near-collapsed dimensions through masking and reweighting of the KL term. Our results show that this intervention significantly increases the number of active latent dimensions without degrading reconstruction accuracy. Ultimately, this will improve understanding of the decisions behind trajectory generation, enabling wider adoption. ...
The development of realistic synthetic trajectory data is essential for the planning and validation of future Air Traffic Management concepts. Deep generative models have emerged as state-of-the-art methods for synthetic trajectory generation due to their ability to learn complex dynamics. In particular, Variational Autoencoders (VAEs) have gained significant attention because of their stable training. However, for the generated data to be trusted, model interpretability is crucial. A key aspect for interpretability is the analysis of the latent space, where the essential features and patterns of trajectory behavior are encoded. However, in practice, many latent dimensions remain weakly utilized or collapse toward the prior, limiting interpretability and effective use of latent capacity.
In this work, we study latent dimension activity in temporal VAEs trained on real-world aircraft trajectory data, with a specific focus on how Kullback-Leibler (KL) divergence regularization, a penalty added to the model’s loss function, affects the number of active latent dimensions. We adopt a temporal convolutional VAE with fixed latent dimensionality and formulate the KL divergence as an average over latent dimensions, thereby controlling the information content per dimension.
Additionally, we introduce a modified training objective that explicitly suppresses near-collapsed dimensions through masking and reweighting of the KL term. Our results show that this intervention significantly increases the number of active latent dimensions without degrading reconstruction accuracy. Ultimately, this will improve understanding of the decisions behind trajectory generation, enabling wider adoption.
In this work, we study latent dimension activity in temporal VAEs trained on real-world aircraft trajectory data, with a specific focus on how Kullback-Leibler (KL) divergence regularization, a penalty added to the model’s loss function, affects the number of active latent dimensions. We adopt a temporal convolutional VAE with fixed latent dimensionality and formulate the KL divergence as an average over latent dimensions, thereby controlling the information content per dimension.
Additionally, we introduce a modified training objective that explicitly suppresses near-collapsed dimensions through masking and reweighting of the KL term. Our results show that this intervention significantly increases the number of active latent dimensions without degrading reconstruction accuracy. Ultimately, this will improve understanding of the decisions behind trajectory generation, enabling wider adoption.
Reactionary delays are a critical challenge in airline operations, especially within hub-spoke networks, where disruptions at spoke airports propagate and amplify throughout the fleet. Accurate prediction of these delays is essential for effective network planning, as errors can lead to flight cancellations, missed connections, and curfew infringements. However, current state-of-the-art delay prediction models do not fully integrate all elements that cause reactionary delays and affect subsequent operations. This study aims to close this gap by using a Graph Attention Network (GAT) model to predict reactionary delay distributions within a fleet network and identify the most critical flights through the analysis of attention weights. Using operational data from Swiss International Air Lines’ short-haul fleet, the GAT model integrates node-level features, such as flight-specific parameters, and edge-level features, including rotational dependencies and passenger connections, to capture the spatial-temporal dynamics of delay propagation. The GAT model achieved reliable predictive accuracy, particularly on medium-delay days, of a root mean squared error of 15.59 minutes and a mean absolute error of 10.50 minutes. The results further reveal that the model comprehends the ripple effects caused by rotation delays. Furthermore, its attention weights confirm its capability to identify critical flights and connections, enabling the airline to allocate resources more effectively.
...
Reactionary delays are a critical challenge in airline operations, especially within hub-spoke networks, where disruptions at spoke airports propagate and amplify throughout the fleet. Accurate prediction of these delays is essential for effective network planning, as errors can lead to flight cancellations, missed connections, and curfew infringements. However, current state-of-the-art delay prediction models do not fully integrate all elements that cause reactionary delays and affect subsequent operations. This study aims to close this gap by using a Graph Attention Network (GAT) model to predict reactionary delay distributions within a fleet network and identify the most critical flights through the analysis of attention weights. Using operational data from Swiss International Air Lines’ short-haul fleet, the GAT model integrates node-level features, such as flight-specific parameters, and edge-level features, including rotational dependencies and passenger connections, to capture the spatial-temporal dynamics of delay propagation. The GAT model achieved reliable predictive accuracy, particularly on medium-delay days, of a root mean squared error of 15.59 minutes and a mean absolute error of 10.50 minutes. The results further reveal that the model comprehends the ripple effects caused by rotation delays. Furthermore, its attention weights confirm its capability to identify critical flights and connections, enabling the airline to allocate resources more effectively.
Conference paper
(2025)
-
C. Dolman, M.J. Ribeiro, Junzi Sun, P.R.J.R. Lothaller, Jasper de Wilde, Alexander Piva, F.A.K. Vossen
Air traffic delays have a major impact on the aviation industry, affecting airlines, passengers, and the broader ecosystem. With increasing regulatory and sustainability pressures, accurate delay predictions are critical as they allow for precise determination of the contingency and discretionary fuel required for flights. This research aims to develop an explainable supervised learning model to improve existing en route delay predictions, focusing on intercontinental flights from North America to Amsterdam Schiphol Airport. While prior studies have explored flight delay prediction, they have not addressed two critical research gaps identified in this research: the inclusion of day-of-operations features, such as passenger information, aircraft weights, and cost index, and the use of transatlantic flight data for predictions 90 minutes before departure. To address these gaps, two Gradient-Boosted models, CatBoost and LightGBM, were trained using internal airline, airport, and METAR data. Both models outperformed the airline’s current in-use statistical model, with CatBoost achieving an MAE of 3.44 minutes and RMSE of 4.61 minutes and LightGBM achieving an MAE of 3.43 minutes and RMSE of 4.56 minutes. The most significant performance increase over the current model was observed under adverse weather conditions. This research advances en route delay prediction by providing more accurate delay forecasts, particularly in critical weather conditions, and proposes practical improvements to support future studies focused on enhancing model adaptability across diverse operational contexts.
...
Air traffic delays have a major impact on the aviation industry, affecting airlines, passengers, and the broader ecosystem. With increasing regulatory and sustainability pressures, accurate delay predictions are critical as they allow for precise determination of the contingency and discretionary fuel required for flights. This research aims to develop an explainable supervised learning model to improve existing en route delay predictions, focusing on intercontinental flights from North America to Amsterdam Schiphol Airport. While prior studies have explored flight delay prediction, they have not addressed two critical research gaps identified in this research: the inclusion of day-of-operations features, such as passenger information, aircraft weights, and cost index, and the use of transatlantic flight data for predictions 90 minutes before departure. To address these gaps, two Gradient-Boosted models, CatBoost and LightGBM, were trained using internal airline, airport, and METAR data. Both models outperformed the airline’s current in-use statistical model, with CatBoost achieving an MAE of 3.44 minutes and RMSE of 4.61 minutes and LightGBM achieving an MAE of 3.43 minutes and RMSE of 4.56 minutes. The most significant performance increase over the current model was observed under adverse weather conditions. This research advances en route delay prediction by providing more accurate delay forecasts, particularly in critical weather conditions, and proposes practical improvements to support future studies focused on enhancing model adaptability across diverse operational contexts.
Optimisation of Preventive A-check Maintenance Tasks
Integrated and Distributed Approaches
A-check maintenance scheduling is a complex and critical undertaking for airlines requiring an efficient allocation of resources. Current state-of-the-art focuses primarily on long-term A-check planning, typically targeting a longer scheduling horizon while foregoing individual task planning. This paper introduces a novel integrated approach for A-check scheduling at a seasonal level for an airline fleet, which accounts for both repetitive and one-off maintenance tasks. The A-check maintenance scheduling problem is formulated as a mixed-integer linear program (MILP), which optimises for minimal interval waste and timely initiation of one-off activities. Furthermore, we explore the scalability and flexibility of this problem by proposing three distinct distributed architectures. Subsets of maintenance tasks are scheduled by individual components, guided by a genetic algorithm (GA) acting as a global optimiser, with each architecture managing shared resources differently. We demonstrate our method with a case study from a major European airline using recent data of a fleet of wide-bodied passenger aircraft. While our MILP baseline produces comparable results to real-world schedules within minutes, the distributed architectures, despite their potential for scalability, generally underperform compared to the central planner. We analyse the degradation of solution quality across these distributed architectures, providing insights into their design limitations and the inherent indivisibility of the problem. We propose that our central MILP-based scheduler can be used by airlines as a decision-support tool for A-check task planning at the seasonal level.
...
A-check maintenance scheduling is a complex and critical undertaking for airlines requiring an efficient allocation of resources. Current state-of-the-art focuses primarily on long-term A-check planning, typically targeting a longer scheduling horizon while foregoing individual task planning. This paper introduces a novel integrated approach for A-check scheduling at a seasonal level for an airline fleet, which accounts for both repetitive and one-off maintenance tasks. The A-check maintenance scheduling problem is formulated as a mixed-integer linear program (MILP), which optimises for minimal interval waste and timely initiation of one-off activities. Furthermore, we explore the scalability and flexibility of this problem by proposing three distinct distributed architectures. Subsets of maintenance tasks are scheduled by individual components, guided by a genetic algorithm (GA) acting as a global optimiser, with each architecture managing shared resources differently. We demonstrate our method with a case study from a major European airline using recent data of a fleet of wide-bodied passenger aircraft. While our MILP baseline produces comparable results to real-world schedules within minutes, the distributed architectures, despite their potential for scalability, generally underperform compared to the central planner. We analyse the degradation of solution quality across these distributed architectures, providing insights into their design limitations and the inherent indivisibility of the problem. We propose that our central MILP-based scheduler can be used by airlines as a decision-support tool for A-check task planning at the seasonal level.
Punctuality is a key performance indicator for any airline, especially hub-and-spoke airlines, given their focus on short passenger connections. Flights that are delayed at departure need to compensate for lost time whilst airborne. Because fuelling takes place well before scheduled departure, predicted departure delays determine the planned fuel amounts for en-route speed optimization. To prevent unnecessary fuel burn, airlines benefit from highly accurate departure delay predictions. This study aims to extend previous work on airline departure delay forecasting to a dynamic and probabilistic domain, whilst incorporating novel day-of-operations airline information to further minimize prediction errors. Random Forest, CatBoost, and Deep Neural Network models are proposed for a case study on departure flights of a major hub-and-spoke airline from its hub airport between 1 January 2020 and 1 August 2023. The Random Forest model is selected for its probabilistic performance and high accuracy in predicting delays between 5 and 25 min, for which en-route speed optimization has the largest effect. At the 90 min prediction horizon, the model reaches a Mean Absolute Error of 8.46 min and a Root Mean Square Error of 11.91 min. For 76% of flights, the actual delay is within the predicted probability distribution range. Finally, this study puts a strong emphasis on explainability. Flight dispatchers are therefore provided with the main factors impacting the prediction, explaining the context of the flight. The versatility of the model is demonstrated in two shadow runs within the procedures of an international airline, where delays caused by familiar and unfamiliar factors were successfully predicted.
...
Punctuality is a key performance indicator for any airline, especially hub-and-spoke airlines, given their focus on short passenger connections. Flights that are delayed at departure need to compensate for lost time whilst airborne. Because fuelling takes place well before scheduled departure, predicted departure delays determine the planned fuel amounts for en-route speed optimization. To prevent unnecessary fuel burn, airlines benefit from highly accurate departure delay predictions. This study aims to extend previous work on airline departure delay forecasting to a dynamic and probabilistic domain, whilst incorporating novel day-of-operations airline information to further minimize prediction errors. Random Forest, CatBoost, and Deep Neural Network models are proposed for a case study on departure flights of a major hub-and-spoke airline from its hub airport between 1 January 2020 and 1 August 2023. The Random Forest model is selected for its probabilistic performance and high accuracy in predicting delays between 5 and 25 min, for which en-route speed optimization has the largest effect. At the 90 min prediction horizon, the model reaches a Mean Absolute Error of 8.46 min and a Root Mean Square Error of 11.91 min. For 76% of flights, the actual delay is within the predicted probability distribution range. Finally, this study puts a strong emphasis on explainability. Flight dispatchers are therefore provided with the main factors impacting the prediction, explaining the context of the flight. The versatility of the model is demonstrated in two shadow runs within the procedures of an international airline, where delays caused by familiar and unfamiliar factors were successfully predicted.
Prediction of Traffic Take-Off Times at Out-Stations
A Case Study at Schiphol Airport
Reducing uncertainty in air traffic flow management is crucial for maintaining safety and efficiency in modern aviation. In particular, forecasting Actual Take-Off Times (ATOT) for flights across Europe is challenging due to the diverse flight-specific variables and operational conditions. Additionally, to help operations, this prediction must be done well in advance in order to prevent future traffic densities from being higher than the airspace capacity. However, recent studies often make predictions on shorter horizons and do not consider the effect of knock-on delays. This study covers this gap, by focusing on larger prediction horizons and different types of delay. We enhance ATOT prediction for flights arriving at Amsterdam Schiphol Airport from European out-stations by leveraging machine learning techniques, specifically a Long Short-Term Memory (LSTM) neural network, augmented with a Multihead Attention mechanism. A model capable of capturing complex temporal dependencies and operational factors influencing the ATOT is developed utilizing data from Electronic Flight Data messages, weather reports and a EUROCONTROL dataset. The model’s performance is evaluated against traditional ensemble methods and the current Decision Support Tool (DST) system used by Luchtverkeersleiding Nederland (LVNL). Results indicate that the LSTM model outperforms existing models including a reproduction of the DST, achieving a Mean Absolute Error of 12.05 minutes at a forecast horizon of 4 hours, demonstrating significant improvements. Finally, this assessment underscores the importance of factors such as the knock-on effect in delay prediction can significantly enhance demand forecasting, leading to more efficient air traffic management and reduced delays.
...
Reducing uncertainty in air traffic flow management is crucial for maintaining safety and efficiency in modern aviation. In particular, forecasting Actual Take-Off Times (ATOT) for flights across Europe is challenging due to the diverse flight-specific variables and operational conditions. Additionally, to help operations, this prediction must be done well in advance in order to prevent future traffic densities from being higher than the airspace capacity. However, recent studies often make predictions on shorter horizons and do not consider the effect of knock-on delays. This study covers this gap, by focusing on larger prediction horizons and different types of delay. We enhance ATOT prediction for flights arriving at Amsterdam Schiphol Airport from European out-stations by leveraging machine learning techniques, specifically a Long Short-Term Memory (LSTM) neural network, augmented with a Multihead Attention mechanism. A model capable of capturing complex temporal dependencies and operational factors influencing the ATOT is developed utilizing data from Electronic Flight Data messages, weather reports and a EUROCONTROL dataset. The model’s performance is evaluated against traditional ensemble methods and the current Decision Support Tool (DST) system used by Luchtverkeersleiding Nederland (LVNL). Results indicate that the LSTM model outperforms existing models including a reproduction of the DST, achieving a Mean Absolute Error of 12.05 minutes at a forecast horizon of 4 hours, demonstrating significant improvements. Finally, this assessment underscores the importance of factors such as the knock-on effect in delay prediction can significantly enhance demand forecasting, leading to more efficient air traffic management and reduced delays.
The European Air Traffic Management system is among the most complex systems in the world. Due to the dense nature of the European network, consequences of disruptions are often catastrophic. In particular, disruptions altering the expected flying time tend to pose great challenges to the arrival management of busy hubs. In response, EUROCONTROL released the Target Time Management (TTM) system, allowing airlines to issue Target Times of Arrival (TTA) even before depart. The TTM system helps hubs airports coordinate arrivals and departures. From the point of view of airlines, the advantage resides in being able to prioritize early arrivals of critical flights. Nevertheless, real-time prioritization is not trivial. Many studies have focused on this problem but with results limited to slot swapping in a tactical context. This is less effective compared to airlines having the ability to select a new slot at the pre-tactical level. This work covers this gap, allowing airlines to select the desired TTA even before departure. We use Deep Reinforcement Learning to create a dynamic arrival allocation model capable of prioritizing flights in terms of passenger connecting time, curfew performance, rotation delay, and fairness to other airlines. Additionally, the model is capable of adapting and react to the uncertainty in responses from the TTM. In the real-world, large anticipations in TTAs are often rejected. The model is tested with real data from SWISS International Airline. Results show an improvement of 5.9 minutes for critical passenger connection and 4.8 minutes for rotation delay versus a deterministic approach.
...
The European Air Traffic Management system is among the most complex systems in the world. Due to the dense nature of the European network, consequences of disruptions are often catastrophic. In particular, disruptions altering the expected flying time tend to pose great challenges to the arrival management of busy hubs. In response, EUROCONTROL released the Target Time Management (TTM) system, allowing airlines to issue Target Times of Arrival (TTA) even before depart. The TTM system helps hubs airports coordinate arrivals and departures. From the point of view of airlines, the advantage resides in being able to prioritize early arrivals of critical flights. Nevertheless, real-time prioritization is not trivial. Many studies have focused on this problem but with results limited to slot swapping in a tactical context. This is less effective compared to airlines having the ability to select a new slot at the pre-tactical level. This work covers this gap, allowing airlines to select the desired TTA even before departure. We use Deep Reinforcement Learning to create a dynamic arrival allocation model capable of prioritizing flights in terms of passenger connecting time, curfew performance, rotation delay, and fairness to other airlines. Additionally, the model is capable of adapting and react to the uncertainty in responses from the TTM. In the real-world, large anticipations in TTAs are often rejected. The model is tested with real data from SWISS International Airline. Results show an improvement of 5.9 minutes for critical passenger connection and 4.8 minutes for rotation delay versus a deterministic approach.
Flight and maintenance scheduling pose conflicting objectives: while maintenance is vital for ensuring aircraft airworthiness, it comes at the cost of taking aircraft out of operation. In current operations, airlines manually handle tail assignment and maintenance task scheduling separately, missing an opportunity to strike a better balance. This division leads to wasted maintenance resources, restricted fleet availability for schedule flexibility, inconsistent planning, and neglect of schedule resilience. This study presents a novel approach that integrates tail assignment and maintenance scheduling into a unified decision-support framework. An integer program, tailored to meet airline-specific requirements and constraints, is combined with an innovative time-space network (TSN). The TSN incorporates two distinct spaces for maintenance and network activities. The primary objective is to generate feasible plans that increase schedule efficiency (i.e., no cancellations, high fleet availability, high fleet health, and optimal use of maintenance resources) and schedule stability (i.e., limited number of late arrival disruptions during operations) the day before operation. Additionally, this framework addresses overlooked aspects in the literature: it treats maintenance tasks as variable interval activities based on aircraft-specific needs, departing from the traditional fixed interval approach. The performance of the framework is tested with real-data provided by a major European single hub-to-spoke airline, with a heterogeneous fleet of over 50 wide-body aircraft. Historical data from arrival delays is used to create robust buffers that mitigate delay propagation. A 17% reduction in maintenance time was achieved compared to the airline’s current plans, resulting in a 10% increase in fleet availability on the day of operations. This improvement is attributed to higher labour and task interval utilization, indicating the framework’s superior efficiency in scheduling maintenance tasks. Lastly, the framework produced plans more resilient to arrival delays, reducing the number of disruptions and delay propagation over 40%. This framework can be used as a decision-support tool for airlines, enabling the creation of schedules that are both robust against delays and optimized for fleet utilization.
...
Flight and maintenance scheduling pose conflicting objectives: while maintenance is vital for ensuring aircraft airworthiness, it comes at the cost of taking aircraft out of operation. In current operations, airlines manually handle tail assignment and maintenance task scheduling separately, missing an opportunity to strike a better balance. This division leads to wasted maintenance resources, restricted fleet availability for schedule flexibility, inconsistent planning, and neglect of schedule resilience. This study presents a novel approach that integrates tail assignment and maintenance scheduling into a unified decision-support framework. An integer program, tailored to meet airline-specific requirements and constraints, is combined with an innovative time-space network (TSN). The TSN incorporates two distinct spaces for maintenance and network activities. The primary objective is to generate feasible plans that increase schedule efficiency (i.e., no cancellations, high fleet availability, high fleet health, and optimal use of maintenance resources) and schedule stability (i.e., limited number of late arrival disruptions during operations) the day before operation. Additionally, this framework addresses overlooked aspects in the literature: it treats maintenance tasks as variable interval activities based on aircraft-specific needs, departing from the traditional fixed interval approach. The performance of the framework is tested with real-data provided by a major European single hub-to-spoke airline, with a heterogeneous fleet of over 50 wide-body aircraft. Historical data from arrival delays is used to create robust buffers that mitigate delay propagation. A 17% reduction in maintenance time was achieved compared to the airline’s current plans, resulting in a 10% increase in fleet availability on the day of operations. This improvement is attributed to higher labour and task interval utilization, indicating the framework’s superior efficiency in scheduling maintenance tasks. Lastly, the framework produced plans more resilient to arrival delays, reducing the number of disruptions and delay propagation over 40%. This framework can be used as a decision-support tool for airlines, enabling the creation of schedules that are both robust against delays and optimized for fleet utilization.
Conference paper
(2025)
-
Phillipe Lothaller, Marta Ribeiro, Junzi Sun, Jasper de Wilde, Alexander Piva
Aircraft carry additional fuel reserves, referred to as contingency fuel, used to account for unforeseen events during a flight. Previous research has attempted to quantify the magnitude of such events, most notably the probability of adverse weather or ATFM regulation, yet their inherent unpredictability introduces uncertainty and frequently results in the overestimation of contingency fuel requirements. Recent studies use data-driven fuel-burn predictions to better estimate contingency fuel sizing; however, most are confined to specific routes or regions, limiting generalizability. To address this, we utilise real operational airline data covering both regional and intercontinental flights, and develop a quantile regression framework for predicting contingency fuel requirements, capable of adapting to more diverse set of flight characteristics. Our framework integrates flight-plan data, TAF weather forecasts, and proxy congestion features to predict required contingency fuel at varying quantile levels, enabling trade-offs between efficiency and safety. Unlike the current Statistical Contingency Fuel process, which applies different coverage levels by risk category, this evaluation uses a single fixed quantile for all flights when generating predictions. In a four-month out-of-sample evaluation, a single fixed quantile matched the safety performance of the Statistical Contingency Fuel process while reducing excess fuel carriage by up to 235,364 kg (≈11%). A more conservative quantile configuration yielded smaller savings but reduced abnormal flight-phase events by 22.2%. The key drivers of the final predictions are evaluated, offering pilots and dispatchers transparent explanations that can build trust and reduce reliance on discretionary fuel loading.
...
Aircraft carry additional fuel reserves, referred to as contingency fuel, used to account for unforeseen events during a flight. Previous research has attempted to quantify the magnitude of such events, most notably the probability of adverse weather or ATFM regulation, yet their inherent unpredictability introduces uncertainty and frequently results in the overestimation of contingency fuel requirements. Recent studies use data-driven fuel-burn predictions to better estimate contingency fuel sizing; however, most are confined to specific routes or regions, limiting generalizability. To address this, we utilise real operational airline data covering both regional and intercontinental flights, and develop a quantile regression framework for predicting contingency fuel requirements, capable of adapting to more diverse set of flight characteristics. Our framework integrates flight-plan data, TAF weather forecasts, and proxy congestion features to predict required contingency fuel at varying quantile levels, enabling trade-offs between efficiency and safety. Unlike the current Statistical Contingency Fuel process, which applies different coverage levels by risk category, this evaluation uses a single fixed quantile for all flights when generating predictions. In a four-month out-of-sample evaluation, a single fixed quantile matched the safety performance of the Statistical Contingency Fuel process while reducing excess fuel carriage by up to 235,364 kg (≈11%). A more conservative quantile configuration yielded smaller savings but reduced abnormal flight-phase events by 22.2%. The key drivers of the final predictions are evaluated, offering pilots and dispatchers transparent explanations that can build trust and reduce reliance on discretionary fuel loading.
Multi-objective vertiport location optimization for a middle-mile package delivery framework
Case study in the South Holland Region
With the rapidly increasing pace of urbanization and high demand for efficient modes of transport, the Urban Air Mobility (UAM) market has seen a remarkable growth in the past years. This is especially the case for the transportation of goods. Using UAM for cargo operations is likely through operating on Middle-Mile Delivery (MMD) missions to transport cargo between facilities or distribution centers in an operator’s network. The efficiency and practicality of such a network are largely affected by the selection of strategic positions for
vertiports. As vertiport location optimization is underexplored in current scientific research this paper aims to fill this research gap by developing and analyzing a multi-objective optimization model for the placement of vertiports for a middle-mile package delivery system, considering capacity, available land space, safety and noise impact factors. We develop a novel Multi-Objective Multiple Allocation Capacitated p-Hub Coverage Problem framework for an MMD UAM network and test it using the South Holland region as a case study. Notably, the model can easily be converted to other cities. First, to reduce computational efforts, the K-means
clustering algorithm is proposed. This is used to divide 6625 zones into a number of K clusters, with each
cluster representing a vertiport candidate location. Furthermore, we present a multi-objective Tabu Search
based heuristic optimization algorithm to solve the optimization problem. The impact of different factors
such as number of clusters, number of vertiports, drone range, maximum safety distance, and turn around
time The presented model provides decision-makers with the ability to assess the suitability of a region
for the implementation of a UAM MMD system and aids in the identification of potential good locations to
set up vertiports. We demonstrate that an increase in the number of vertiports leads to a higher attainable
demand coverage, however, this results in a steep drop-off in terms of safety and noise nuisance performance.
Furthermore, the results show that an increase in drone range, maximum safety distance or a decrease in turn
around time allow for overall better performing vertiport networks. ...
vertiports. As vertiport location optimization is underexplored in current scientific research this paper aims to fill this research gap by developing and analyzing a multi-objective optimization model for the placement of vertiports for a middle-mile package delivery system, considering capacity, available land space, safety and noise impact factors. We develop a novel Multi-Objective Multiple Allocation Capacitated p-Hub Coverage Problem framework for an MMD UAM network and test it using the South Holland region as a case study. Notably, the model can easily be converted to other cities. First, to reduce computational efforts, the K-means
clustering algorithm is proposed. This is used to divide 6625 zones into a number of K clusters, with each
cluster representing a vertiport candidate location. Furthermore, we present a multi-objective Tabu Search
based heuristic optimization algorithm to solve the optimization problem. The impact of different factors
such as number of clusters, number of vertiports, drone range, maximum safety distance, and turn around
time The presented model provides decision-makers with the ability to assess the suitability of a region
for the implementation of a UAM MMD system and aids in the identification of potential good locations to
set up vertiports. We demonstrate that an increase in the number of vertiports leads to a higher attainable
demand coverage, however, this results in a steep drop-off in terms of safety and noise nuisance performance.
Furthermore, the results show that an increase in drone range, maximum safety distance or a decrease in turn
around time allow for overall better performing vertiport networks. ...
With the rapidly increasing pace of urbanization and high demand for efficient modes of transport, the Urban Air Mobility (UAM) market has seen a remarkable growth in the past years. This is especially the case for the transportation of goods. Using UAM for cargo operations is likely through operating on Middle-Mile Delivery (MMD) missions to transport cargo between facilities or distribution centers in an operator’s network. The efficiency and practicality of such a network are largely affected by the selection of strategic positions for
vertiports. As vertiport location optimization is underexplored in current scientific research this paper aims to fill this research gap by developing and analyzing a multi-objective optimization model for the placement of vertiports for a middle-mile package delivery system, considering capacity, available land space, safety and noise impact factors. We develop a novel Multi-Objective Multiple Allocation Capacitated p-Hub Coverage Problem framework for an MMD UAM network and test it using the South Holland region as a case study. Notably, the model can easily be converted to other cities. First, to reduce computational efforts, the K-means
clustering algorithm is proposed. This is used to divide 6625 zones into a number of K clusters, with each
cluster representing a vertiport candidate location. Furthermore, we present a multi-objective Tabu Search
based heuristic optimization algorithm to solve the optimization problem. The impact of different factors
such as number of clusters, number of vertiports, drone range, maximum safety distance, and turn around
time The presented model provides decision-makers with the ability to assess the suitability of a region
for the implementation of a UAM MMD system and aids in the identification of potential good locations to
set up vertiports. We demonstrate that an increase in the number of vertiports leads to a higher attainable
demand coverage, however, this results in a steep drop-off in terms of safety and noise nuisance performance.
Furthermore, the results show that an increase in drone range, maximum safety distance or a decrease in turn
around time allow for overall better performing vertiport networks.
vertiports. As vertiport location optimization is underexplored in current scientific research this paper aims to fill this research gap by developing and analyzing a multi-objective optimization model for the placement of vertiports for a middle-mile package delivery system, considering capacity, available land space, safety and noise impact factors. We develop a novel Multi-Objective Multiple Allocation Capacitated p-Hub Coverage Problem framework for an MMD UAM network and test it using the South Holland region as a case study. Notably, the model can easily be converted to other cities. First, to reduce computational efforts, the K-means
clustering algorithm is proposed. This is used to divide 6625 zones into a number of K clusters, with each
cluster representing a vertiport candidate location. Furthermore, we present a multi-objective Tabu Search
based heuristic optimization algorithm to solve the optimization problem. The impact of different factors
such as number of clusters, number of vertiports, drone range, maximum safety distance, and turn around
time The presented model provides decision-makers with the ability to assess the suitability of a region
for the implementation of a UAM MMD system and aids in the identification of potential good locations to
set up vertiports. We demonstrate that an increase in the number of vertiports leads to a higher attainable
demand coverage, however, this results in a steep drop-off in terms of safety and noise nuisance performance.
Furthermore, the results show that an increase in drone range, maximum safety distance or a decrease in turn
around time allow for overall better performing vertiport networks.
The complexity of airline operations requires operations planning to be divided into multiple problems solved sequentially by the respective departments. This is particularly the case for (1) network planning and (2) maintenance planning. Despite the close interaction of these two departments, airlines typically evaluate plans from both domains separately. However, an integrated perspective is necessary to develop robust plans and effective recovery policies in this intrinsically uncertain environment. This paper presents a new modular, stochastic, discrete event simulation model of airline operations named ANEMOS (Airline Network and Maintenance Operations Simulation). ANEMOS contains both network and maintenance dynamics, allowing the evaluation of plans, policies, and scenarios from both domains. The model is validated using data from a major European airline. We show that the simulated results closely resemble the airline's historical operational performance. ANEMOS is tested with a use-case investigating the effects of adding a second reserve aircraft to a fleet of fifty wide-body aircraft. The results show that the second reserve is capable of reducing cancellations by 55%. However, such does not cover the lost revenue associated with keeping an aircraft non-operational for a part of the time.
...
The complexity of airline operations requires operations planning to be divided into multiple problems solved sequentially by the respective departments. This is particularly the case for (1) network planning and (2) maintenance planning. Despite the close interaction of these two departments, airlines typically evaluate plans from both domains separately. However, an integrated perspective is necessary to develop robust plans and effective recovery policies in this intrinsically uncertain environment. This paper presents a new modular, stochastic, discrete event simulation model of airline operations named ANEMOS (Airline Network and Maintenance Operations Simulation). ANEMOS contains both network and maintenance dynamics, allowing the evaluation of plans, policies, and scenarios from both domains. The model is validated using data from a major European airline. We show that the simulated results closely resemble the airline's historical operational performance. ANEMOS is tested with a use-case investigating the effects of adding a second reserve aircraft to a fleet of fifty wide-body aircraft. The results show that the second reserve is capable of reducing cancellations by 55%. However, such does not cover the lost revenue associated with keeping an aircraft non-operational for a part of the time.
Assigning aircraft to gates is one of the most important daily decision problems that airport professionals face. The solution to this problem has raised a significant effort, with many researchers tackling many different variants of this problem. However, most existing studies on gate assignment contain only a static perspective without considering possible future disruptions and uncertainties. We bridge this gap by looking at gate assignments as a dynamic decision-making process. This paper presents the Real-time Gate Assignment Problem Solution (REGAPS) algorithm, an innovative method adept at resolving pre-assignment issues and dynamically optimizing gate assignments in real-time at airports through the integration of Deep Reinforcement Learning (DRL). This work represents the first time that DRL is used with real airport data and a configuration containing a large number of flights and gates. The methodology combines a tailored Markov Decision Process (MDP) formulation with the Asynchronous Advantage Actor–Critic (A3C) architecture. Multiple factors, such as flight schedules, gate availability, and passenger walking time, are considered. An empirical case study demonstrates that the REGAPS outperforms two classic deep Q-learning algorithms and a traditional Genetic Algorithm in terms of reducing passenger walking time and apron gate assignment. Finally, supplementary experiments highlight REGAPS’s adaptability under various gate assignment rules for international and domestic flights. The finding demonstrates that not only did REGAPS outperform COVID restrictions, but it can also produce considerable benefits under other policies.
...
Assigning aircraft to gates is one of the most important daily decision problems that airport professionals face. The solution to this problem has raised a significant effort, with many researchers tackling many different variants of this problem. However, most existing studies on gate assignment contain only a static perspective without considering possible future disruptions and uncertainties. We bridge this gap by looking at gate assignments as a dynamic decision-making process. This paper presents the Real-time Gate Assignment Problem Solution (REGAPS) algorithm, an innovative method adept at resolving pre-assignment issues and dynamically optimizing gate assignments in real-time at airports through the integration of Deep Reinforcement Learning (DRL). This work represents the first time that DRL is used with real airport data and a configuration containing a large number of flights and gates. The methodology combines a tailored Markov Decision Process (MDP) formulation with the Asynchronous Advantage Actor–Critic (A3C) architecture. Multiple factors, such as flight schedules, gate availability, and passenger walking time, are considered. An empirical case study demonstrates that the REGAPS outperforms two classic deep Q-learning algorithms and a traditional Genetic Algorithm in terms of reducing passenger walking time and apron gate assignment. Finally, supplementary experiments highlight REGAPS’s adaptability under various gate assignment rules for international and domestic flights. The finding demonstrates that not only did REGAPS outperform COVID restrictions, but it can also produce considerable benefits under other policies.
Reactionary delays are a critical challenge in airline operations, especially within hub-spoke networks, where disruptions at spoke airports propagate and amplify throughout the fleet. Accurate prediction of these delays is essential for effective network planning, as errors can lead to flight cancellations, missed connections, and curfew infringements. However, current state-of-the-art delay prediction models do not fully integrate all elements that cause reactionary delays and affect subsequent operations. This study aims to close this gap by using a Graph Attention Network (GAT) model to predict reactionary delay distributions within a fleet network and identify the most critical flights through the analysis of attention weights. Using operational data from Swiss International Air Lines’ shorthaul fleet, the GAT model integrates node-level features, such as flight-specific parameters, and edge-level features, including rotational dependencies and passenger connections, to capture the spatial-temporal dynamics of delay propagation. The GAT model achieved reliable predictive accuracy, particularly on medium-delay days, of a root mean squared error of 15.59 minutes and a mean absolute error of 10.50 minutes. The results further reveal that the model comprehends the ripple effects caused by rotation delays. Furthermore, its attention weights confirm its capability to identify critical flights and connections, enabling the airline to allocate resources more effectively.
...
Reactionary delays are a critical challenge in airline operations, especially within hub-spoke networks, where disruptions at spoke airports propagate and amplify throughout the fleet. Accurate prediction of these delays is essential for effective network planning, as errors can lead to flight cancellations, missed connections, and curfew infringements. However, current state-of-the-art delay prediction models do not fully integrate all elements that cause reactionary delays and affect subsequent operations. This study aims to close this gap by using a Graph Attention Network (GAT) model to predict reactionary delay distributions within a fleet network and identify the most critical flights through the analysis of attention weights. Using operational data from Swiss International Air Lines’ shorthaul fleet, the GAT model integrates node-level features, such as flight-specific parameters, and edge-level features, including rotational dependencies and passenger connections, to capture the spatial-temporal dynamics of delay propagation. The GAT model achieved reliable predictive accuracy, particularly on medium-delay days, of a root mean squared error of 15.59 minutes and a mean absolute error of 10.50 minutes. The results further reveal that the model comprehends the ripple effects caused by rotation delays. Furthermore, its attention weights confirm its capability to identify critical flights and connections, enabling the airline to allocate resources more effectively.
Aircraft maintenance scheduling is a focus point for airlines. Maintenance is essential to ensure the airworthiness of aircraft, but it comes at the cost of rendering them unavailable for operations. In current operations, aircraft maintenance scheduling must often be updated to include time for non-routine and non-schedule tasks. These non-routine tasks can increase costs, maintenance workload, and uncertainty of the airlines’ operations. This research introduces a supervised learning framework designed to forecast future non-routine task workloads accurately, improving the accuracy of the planned maintenance schedule. This framework consists of two random forest predictors which estimate the amount of non-routine tasks and the number of future work hours that should be allocated in advance for potential non-routine tasks. Our approach produces highly reliable predictions by leveraging a robust dataset obtained from an international airline. The results show an average of 20% improvement versus an existing on-site sampling method. Furthermore, our in-depth analysis of prediction distributions enables the identification of the underlying causes of significant prediction errors, shedding light on the unpredictabilities inherent to non-routine tasks.
...
Aircraft maintenance scheduling is a focus point for airlines. Maintenance is essential to ensure the airworthiness of aircraft, but it comes at the cost of rendering them unavailable for operations. In current operations, aircraft maintenance scheduling must often be updated to include time for non-routine and non-schedule tasks. These non-routine tasks can increase costs, maintenance workload, and uncertainty of the airlines’ operations. This research introduces a supervised learning framework designed to forecast future non-routine task workloads accurately, improving the accuracy of the planned maintenance schedule. This framework consists of two random forest predictors which estimate the amount of non-routine tasks and the number of future work hours that should be allocated in advance for potential non-routine tasks. Our approach produces highly reliable predictions by leveraging a robust dataset obtained from an international airline. The results show an average of 20% improvement versus an existing on-site sampling method. Furthermore, our in-depth analysis of prediction distributions enables the identification of the underlying causes of significant prediction errors, shedding light on the unpredictabilities inherent to non-routine tasks.
Despite its success in various research domains, Reinforcement Learning (RL) faces challenges in its application to air transport operations due to the rigorous certification standards of the aviation industry. The existing regulatory framework fails to provide adequate, acceptable means of compliance for RL applications, and thus, there is no legal framework for their safe deployment yet. Guidelines must be formulated to certify RL models aimed at air transport operations to enable real-world utilisation of these promising methods. These guidelines must consider the unique characteristics of these models, deviating from the methodology of current guidelines crafted before the emergence of ML applications. The paper proposes novel certification requirements for RL models based on their technical characteristics, safety-criticality, and autonomy. This framework covers the choice of the RL algorithm and analyses the actions, agents, environment, and potential hazards and risks of the RL application. Additionally, this work outlines the evidence the certification applicant must present to demonstrate compliance with these requirements. While this framework is not a complete solution for the complex problem of certifying RL, it is intended to serve as an initial framework which can be extended in cooperation with regulatory entities.
...
Despite its success in various research domains, Reinforcement Learning (RL) faces challenges in its application to air transport operations due to the rigorous certification standards of the aviation industry. The existing regulatory framework fails to provide adequate, acceptable means of compliance for RL applications, and thus, there is no legal framework for their safe deployment yet. Guidelines must be formulated to certify RL models aimed at air transport operations to enable real-world utilisation of these promising methods. These guidelines must consider the unique characteristics of these models, deviating from the methodology of current guidelines crafted before the emergence of ML applications. The paper proposes novel certification requirements for RL models based on their technical characteristics, safety-criticality, and autonomy. This framework covers the choice of the RL algorithm and analyses the actions, agents, environment, and potential hazards and risks of the RL application. Additionally, this work outlines the evidence the certification applicant must present to demonstrate compliance with these requirements. While this framework is not a complete solution for the complex problem of certifying RL, it is intended to serve as an initial framework which can be extended in cooperation with regulatory entities.